Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1597 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0542. Min Act: -0.0003

Data Index: 128101 (C4 (Web Text))

Max Activating Token Index: 126

Text #1

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0449. Min Act: -0.0003

Data Index: 826564 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0425. Min Act: -0.0003

Data Index: 847125 (C4 (Web Text))

Max Activating Token Index: 684

Text #3

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0453. Min Act: -0.0004

Data Index: 1284057 (C4 (Web Text))

Max Activating Token Index: 772

Text #4

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0449. Min Act: -0.0003

Data Index: 1316675 (C4 (Web Text))

Max Activating Token Index: 740

Text #5

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0429. Min Act: -0.0003

Data Index: 259481 (C4 (Web Text))

Max Activating Token Index: 187

Text #6

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0413. Min Act: -0.0003

Data Index: 1181541 (C4 (Web Text))

Max Activating Token Index: 908

Text #7

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0449. Min Act: -0.0003

Data Index: 937416 (C4 (Web Text))

Max Activating Token Index: 518

Text #8

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0440. Min Act: -0.0003

Data Index: 1104650 (C4 (Web Text))

Max Activating Token Index: 95

Text #9

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0435. Min Act: -0.0004

Data Index: 385915 (C4 (Web Text))

Max Activating Token Index: 1014

Text #10

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0456. Min Act: -0.0003

Data Index: 860182 (C4 (Web Text))

Max Activating Token Index: 669

Text #11

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0442. Min Act: -0.0003

Data Index: 858086 (C4 (Web Text))

Max Activating Token Index: 238

Text #12

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0435. Min Act: -0.0003

Data Index: 683786 (C4 (Web Text))

Max Activating Token Index: 70

Text #13

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0441. Min Act: -0.0003

Data Index: 782943 (C4 (Web Text))

Max Activating Token Index: 691

Text #14

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0427. Min Act: -0.0003

Data Index: 111727 (C4 (Web Text))

Max Activating Token Index: 378

Text #15

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0432. Min Act: -0.0003

Data Index: 617502 (C4 (Web Text))

Max Activating Token Index: 492

Text #16

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0434. Min Act: -0.0004

Data Index: 1217796 (C4 (Web Text))

Max Activating Token Index: 175

Text #17

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0396. Min Act: -0.0003

Data Index: 610899 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0424. Min Act: -0.0003

Data Index: 21474 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0423. Min Act: -0.0003

Data Index: 541450 (C4 (Web Text))

Max Activating Token Index: 51